ECE 590: Generative AI: Foundations, Applications, and Safety (Spring 2026)


Instructor

Neil Gong, [email protected]

Teaching Assistant

Reachal Wang, [email protected]
Jason Wang, [email protected]

Lectures

Time: MoWe 3:05PM - 4:20PM.
Location: Teer 203

Office Hours

Time: Wed. 11:00AM - 11:50AM.
Location: 413 Wilkinson Building

Tentative Schedule

01/07    Overview [PDF]

01/12    Transformer 01/14    LLM pre-training and post-training 01/19    Holiday. No class 01/21    LLM agent 01/26    Prompt injection attacks 01/28    Fine-tuning LLMs to be secure against prompt injection attacks 02/02    Detecting and localizing prompt injection attacks 02/04    Adaptive prompt injection attacks 02/09    Jailbreak attacks to LLM 02/11    Defenses against jailbreak attacks 02/16    AI-generated text detection: passive detectors 02/18    AI-generated text detection: watermarks 02/23    Robustness of AI-generated text detectors 02/25    VAE, Dino, and CLIP 03/02    Image generation 03/04    Safety guardrails for image generation models 03/09    Spring recess 03/11    Spring recess 03/16    Jailbreaking safety guardrails of image generation models 03/18    AI-generated image detection: passive methods 03/23    AI-generated image detection: watermarks 03/25    Robustness of AI-generated image detectors 03/30    Data-use auditing: passive methods 04/01    Data-use auditing: proactive methods 04/06    Audio generation and safety issues 04/08    Video generation and safety issues 04/13    Project presentation 04/15    Project presentation

Prerequisite

ECE 580 or 687D or Computer Science 371 or graduate standing.

Course Description

Generative AI is revolutionizing content creation by enabling machines to generate text, images, videos, music, and even code. In this course, we will discuss foundations, applications, and safety and security of generative AI.

Class Format

The class is structured around paper reading, lectures, discussions, and projects. Each lecture will focus on a specific topic, with students expected to read the suggested papers and submit their comments to a designated email address by the end of the day before the lecture. Students will be required to lead a lecture on a chosen topic, complete a class project, present their project, and write a project report. Groups of up to four students can be formed for both the lecture and the class project.

Deadlines

Reading assignments Choosing a topic for lecture Class project

Grading Policy

50% project
25% reading assignment
10% class participation
15% class presentation